Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/fatihkan/badiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/fatihkan/badi/review)<a href="https://agentmods.dev/commands/fatihkan/badi/review"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/review.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02794 |
| Opus 5 | $0.00000 | $0.01397 |
| Sonnet 5 | $0.00000 | $0.00559 |
| Haiku 4.5 | $0.00000 | $0.00279 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep code review command. Comprehensive code analysis across security, performance, and architecture.
Argument format (v1.31.0+):
/review [effort] [--comment] [--correctness-only]
effort:low|medium(default) |high— analysis depth--comment: post findings as inline comments on the active PR (requires the gh CLI)--correctness-only: run only the correctness channel (Channel D) — the single definition lives in Step 0
Difference vs. Anthropic's native
/code-review(Claude Code 2.1.147+):
/code-review: correctness bugs + effort tuning +--comment(native English render)/review(badi): a superset of the above — 4 channels (correctness + security + performance + architecture) + structured report + classification/review --correctness-onlycovers the same ground as/code-review(Channel D only); the full/reviewadds the security, performance, and architecture channels on top of it
Required Tools
- Read (code reading)
- Grep (pattern search)
- Glob (file scan)
- Bash (git diff, gh CLI inline PR comments, analysis tools)
Procedure (4 Steps + optional PR Comment)
Step 0: Argument Parse + Effort & Mode (v1.31.0+)
Note: This command is interpreted by Claude in prompt context — there is no code-based argument parsing. The arguments arrive as "review high --comment" and Claude applies the behavior described in this procedure.
Command arguments:
effort(positional):low|medium|highlow: only CRITICAL + HIGH findings; fast pass over the performance/architecture channelsmedium(default): current behavior — CRITICAL + HIGH + MEDIUM classeshigh: all classes (CRITICAL/HIGH/MEDIUM/LOW) + positive observations + alternative solutions
--comment: enables Step 5 (PR inline comments)--correctness-only(the single definition — every other mention of the flag points here): in Step 3 run only Channel D (Correctness). Skip Channel A (security), Channel B (performance), and Channel C (architecture) entirely — their findings are neither collected nor reported, so a given diff always produces the same verdict for the same flags. The Step 4 approval state is then derived from Channel D findings alone.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 222 lines · 0 tokens per session scan A 2d1ff724d6c6
review is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,794 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other commands, from other repositories
sonarqube
Analyze SonarCloud quality issues for a specific PR.
review-pr
Perform a comprehensive code review of a pull request.
pr
Analyze changes, detect scope issues, and create a well-structured PR.
refactor
Analyze code for SOLID violations and suggest targeted improvements.
audit-codebase
Codebase health audit scoring 7 categories with progression plan.
git-worktree-clean
Clean up stale git worktrees with merged branch detection and disk usage report.